CompassioninMachineLearning/OLMo-3-7B-CPT-BF16_olddata
Full fine-tune vs allenai/Olmo-3-1025-7B. Fine-tune: 94% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, MLP 96/96, Norms 0/129, Attention 128/128, lm_head 1/1
Full fine-tune vs allenai/Olmo-3-1025-7B. Fine-tune: 94% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, MLP 96/96, Norms 0/129, Attention 128/128, lm_head 1/1